Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 581 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.8228. Min Act: -0.1700

Data Index: 1655764 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7915. Min Act: -0.1700

Data Index: 1455660 (Python Code)

Max Activating Token Index: 193

Text #2

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.8540. Min Act: -0.1700

Data Index: 1491084 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1539242 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7915. Min Act: -0.1700

Data Index: 1569245 (Python Code)

Max Activating Token Index: 191

Text #5

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7290. Min Act: -0.1700

Data Index: 1580154 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7290. Min Act: -0.1700

Data Index: 1398353 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1571876 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1441318 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1551399 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1583888 (Python Code)

Max Activating Token Index: 157

Text #11

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1372638 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7603. Min Act: -0.1700

Data Index: 1469813 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.7290. Min Act: -0.1700

Data Index: 1602227 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1494604 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6665. Min Act: -0.1700

Data Index: 1490977 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6665. Min Act: -0.1700

Data Index: 1488563 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1486955 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1565738 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 5.8540. Min Range: -5.8540

Max Act: 5.6978. Min Act: -0.1700

Data Index: 1562311 (Python Code)

Max Activating Token Index: 243